Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19218
    Prev
    Next
    INDEX
    Explanations

    words related to postponement or delay in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of postponement or delays in actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.85
    gdala
    -0.84
    renheit
    -0.82
    ãĥĦ
    -0.82
    rompt
    -0.76
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    minus
    -0.73
    oiler
    -0.73
    ãĤ±
    -0.73
    ictionary
    -0.72
    POSITIVE LOGITS
     gratification
    1.33
     approvals
    1.33
     executions
    1.32
     completion
    1.29
     implementation
    1.27
     issuance
    1.15
     deliveries
    1.13
     enactment
    1.13
     commencement
    1.12
     deport
    1.11
    Activations Density 0.174%

    No Known Activations